Spatial and orientational heterogeneity in the statistical sensitivity of skeleton-based analyses of diffusion tensor MR imaging data

Group comparisons of indices derived from diffusion tensor imaging are common in the literature. An increasingly popular approach to performing such comparisons is the skeleton-projection based approach where, for example, fractional anisotropy (FA) values are projected onto a skeletonized version of the data to minimize differences due to spatial misalignment. In this work, we examine the spatial heterogeneity of the statistical power to detect group differences, and show that there is an intrinsic spatial heterogeneity, with more 'central' structures having less variance within a population. Importantly, we also demonstrate a previously unreported feature of skeleton-based analysis methods, that is that the width of the skeleton depends on the relative orientation to the imaging matrix. Due to the way in which the inferential statistics are performed, this means that structures that are obliquely oriented to the imaging matrix are more likely to show significant differences than when aligned with the imaging matrix. This has profound implications for the interpretation of results obtained from such analysis, especially when there are no a priori hypotheses concerning the spatial location of any group differences. For a uniform (DC) offset between two groups, the skeleton projection-based approaches will be most likely to reveal a difference in centrally located white matter structures oriented obliquely to the imaging matrix.

► Statistical sensitivity of skeleton-based diffusion MRI analyses is shown to be spatially varying. ► Variance of diffusion metrics (e.g. FA) is non-uniform across the skeleton. ► Skeletonization is rotationally variant due to interaction between the imaging matrix and tract orientation. ► Statistical methods using neighbour information can lead to orientational bias of statistical power.